Just heard this story from a colleague, and his motivation is, for the machine learning people, "don't put loops in your Bayesian networks." But for everybody else, simply be careful while dealing with loops...
Prediction For a Cold Winter
The Indians asked their Chief in autumn if the winter was going to be cold or not. Not really knowing the answer, the chief replied that the winter was going to be cold and that the members of the village were to collect wood to be prepared.
Being a good leader, he then went to the phone, called the National Weather Service and asked, "Is this winter going to be cold?" The man on the phone responded, "This winter is going to be quite cold indeed."
So the Chief went back to speed up his people to collect even more wood to be well prepared. A week later he called the National Weather Service again, "Is it really going to be a very cold winter?" "Yes", the man replied, "it's going to be a very cold winter."
So the Chief went back to his people and ordered them to go and collect every scrap of wood they could find. Two weeks later he called the National Weather Service again: "Are you absolutely sure that the winter is going to be very cold?"
"Absolutely," the man replied, "the Indians are collecting wood like crazy!"
- Re: A cold winter storyposted on 01/26/2009
haha, what a cute joke!
are you in machine learning? - Re: A cold winter storyposted on 01/26/2009
kinda, among others...
Please paste HTML code and press Enter.
(c) 2010 Maya Chilam Foundation